Legal claims defining the scope of protection. Each claim is shown in both the original legal language and a plain English translation.
1. A method, performed by a Mobile Edge Computing (MEC) orchestrator, comprising: acquiring MEC computation-related information and User Equipment (UE) mobility-related information from an MEC system including a plurality of MEC entities; performing a classification procedure, based on the MEC computation-related information and the UE mobility-related information, to determine a behavior type of a UE, the behavior type indicating whether to trigger a handover (HO) in the MEC system and whether to trigger a Virtual Machine (VM) migration in the MEC system; comparing a system computation loading with one or more loading thresholds to determine a system computation loading level; performing one of a plurality of adjustment procedures m response to the system computation loading level, wherein the adjustment procedures include: a first adjustment procedure to turn off a computation node of a first MEC entity that operates in an idle state; a second adjustment procedure to adjust an operation state of a second MEC entity in response to an adjustment request from the second MEC entity; and a third adjustment procedure to offload a computation loading from a third MEC entity to a fourth MEC entity; and providing an instruction table in response to the behavior type, the instruction table including routing information for routing MEC traffic among one or more of the plurality of MEC entities.
This invention relates to Mobile Edge Computing (MEC) systems, specifically addressing the challenges of managing computation and mobility in dynamic environments. The method is performed by an MEC orchestrator, which collects computation-related and mobility-related information from multiple MEC entities. Using this data, the orchestrator classifies the behavior of User Equipment (UE) to determine whether to trigger a handover (HO) or a Virtual Machine (VM) migration within the MEC system. The orchestrator also evaluates system computation loading by comparing it against predefined thresholds to determine the loading level. Based on this assessment, it selects one of several adjustment procedures: turning off an idle computation node, adjusting the operation state of a requesting MEC entity, or offloading computation from one MEC entity to another. Additionally, the orchestrator generates an instruction table containing routing information to manage MEC traffic among the entities, ensuring efficient resource utilization and seamless service continuity. The system optimizes performance by dynamically adapting to UE mobility and computation demands, reducing latency and improving resource efficiency.
2. The method of claim 1 , wherein the instruction table comprises a VM identity (ID), a UE ID, and a task tag associated with the routing information.
A system and method for managing virtual machine (VM) and user equipment (UE) task routing in a networked computing environment. The technology addresses the challenge of efficiently directing computational tasks between VMs and UEs in a distributed system, ensuring proper task allocation and routing based on identity and context. The method involves generating an instruction table that includes a VM identity (ID), a UE ID, and a task tag associated with routing information. The VM ID uniquely identifies a virtual machine within the network, while the UE ID identifies a specific user device. The task tag categorizes the type of task being routed, and the routing information specifies how the task should be directed between the VM and UE. This table enables the system to dynamically assign and track tasks, ensuring they are routed to the correct destinations based on their identities and associated metadata. The system may also include mechanisms for updating the instruction table in real-time as tasks are completed or new tasks are generated, maintaining accurate routing information across the network. This approach improves task management efficiency and reduces errors in task allocation within distributed computing environments.
3. The method of claim 2 , wherein the task tag is generated from the UE ID and the VM ID.
A system and method for managing task execution in a virtualized network environment addresses the challenge of efficiently tracking and prioritizing tasks across multiple virtual machines (VMs) and user equipment (UE) devices. The invention involves generating a unique task tag for each task, which is derived from both the UE identifier (ID) and the VM ID. This tagging mechanism ensures that tasks can be uniquely identified and associated with their respective UE and VM, enabling better task management, scheduling, and resource allocation. The task tag may be used to prioritize tasks, route them to the appropriate VM, or monitor their execution status. By combining the UE ID and VM ID, the system ensures that tasks are correctly mapped to their originating devices and processing environments, reducing errors and improving efficiency in task handling. The method may also include additional steps such as validating the task tag, storing task metadata, or dynamically adjusting task priorities based on network conditions. This approach enhances task traceability and system performance in virtualized networks.
4. The method of claim 3 , wherein the task tag is generated by multiplying the UE ID and the VM ID.
A system and method for task tag generation in a virtualized network environment addresses the challenge of uniquely identifying tasks associated with user equipment (UE) and virtual machines (VMs) to ensure proper task routing and management. The invention involves generating a task tag by combining a unique identifier for the UE and a unique identifier for the VM. Specifically, the task tag is created by multiplying the UE ID and the VM ID, producing a composite identifier that links the task to both the originating device and the virtualized execution environment. This method ensures that tasks can be distinctly tracked and managed within a network where multiple UEs interact with multiple VMs, preventing conflicts and enabling efficient task processing. The system may also include mechanisms for validating the task tag to confirm its integrity and authenticity, ensuring that tasks are correctly routed and executed. The invention is particularly useful in cloud computing, edge computing, and other distributed computing environments where task identification and management are critical for performance and security.
5. The method of claim 2 , wherein the instruction table further comprises an MEC entity ID.
A system and method for managing mobile edge computing (MEC) resources involves dynamically allocating and deallocating computational resources based on workload demands. The system includes a controller that monitors resource usage and adjusts allocations to optimize performance. The method involves generating an instruction table that specifies resource assignments, including an MEC entity identifier (MEC entity ID) to uniquely identify the MEC entity associated with the resource allocation. The instruction table is used to configure and manage the MEC infrastructure, ensuring efficient resource utilization and minimizing latency for edge computing applications. The system may also include a monitoring module to track resource usage and a decision engine to determine optimal allocation strategies. The MEC entity ID allows the system to precisely target and manage specific MEC entities within the network, improving coordination and reducing conflicts in resource allocation. This approach enhances scalability and reliability in edge computing environments by dynamically adapting to changing workload conditions.
6. The method of claim 1 , wherein the routing information includes: a first routing path indicating a first pair of MEC entities between which a computation loading is to be transmitted, and a second routing path indicating a second pair of MEC entities between which a computation result of the computation loading is to be transmitted.
This invention relates to multi-access edge computing (MEC) systems, specifically addressing the challenge of efficiently routing computation tasks and their results between MEC entities to optimize performance and reduce latency. The method involves dynamically managing routing information to facilitate the transfer of computation workloads and their corresponding results across distributed MEC nodes. The routing information includes a first routing path that identifies a pair of MEC entities responsible for transmitting a computation workload. This path ensures that the workload is directed to the appropriate MEC entity for processing. Additionally, the routing information includes a second routing path that specifies another pair of MEC entities for transmitting the computation result back to the requesting entity or another designated MEC node. This dual-path routing mechanism enables efficient workload distribution and result retrieval, minimizing delays and improving overall system responsiveness. By defining distinct paths for workload transmission and result retrieval, the method ensures that computation tasks are processed at the optimal MEC entity while results are routed back efficiently. This approach enhances resource utilization and reduces network congestion, particularly in environments where low-latency processing is critical. The invention is particularly useful in scenarios requiring real-time data processing, such as autonomous vehicles, augmented reality, and industrial automation.
7. The method of claim 1 , wherein the plurality of loading thresholds comprises a first loading threshold and a second loading threshold lower than the first loading threshold, and the method further comprises: performing the first adjustment procedure when the system computation loading is lower than or equal to the second loading threshold; performing the second adjustment procedure when the system computation loading is between the first loading threshold and the second loading threshold and the adjustment request is received; and performing the third adjustment procedure when the system computation loading is greater than or equal to the first loading threshold.
This invention relates to dynamic adjustment of system computation loading in a computing environment. The problem addressed is efficiently managing computational resources to optimize performance while preventing system overload. The method involves monitoring system computation loading and applying different adjustment procedures based on predefined loading thresholds. The system uses a first loading threshold and a second, lower loading threshold to determine the appropriate adjustment procedure. When the system computation loading is below or equal to the second threshold, a first adjustment procedure is performed to optimize resource allocation. If the loading is between the first and second thresholds and an adjustment request is received, a second adjustment procedure is executed to balance performance and resource usage. When the loading exceeds or meets the first threshold, a third adjustment procedure is triggered to prevent system overload by prioritizing critical operations and reducing non-essential tasks. The method ensures that computational resources are dynamically allocated based on real-time loading conditions, improving efficiency and system stability. The thresholds and adjustment procedures are designed to adapt to varying workloads, ensuring optimal performance across different operational states. This approach helps maintain system responsiveness while avoiding resource exhaustion.
8. The method of claim 1 , wherein the classification procedure includes: determining, according to the MEC computation-related information, whether a computation loading distributed from the UE is to be computed on one of the plurality of MEC entities; and determining, according to the UE mobility-related information, whether the UE leaves a coverage area of the one of the plurality of MEC entities.
This invention relates to mobile edge computing (MEC) systems, specifically optimizing computation offloading decisions based on both computation load and user equipment (UE) mobility. The problem addressed is inefficient resource allocation in MEC environments, where computation tasks are offloaded to edge servers without considering real-time mobility patterns, leading to performance degradation when UEs move out of coverage areas. The method involves a classification procedure that evaluates two key factors: computation-related information and UE mobility-related information. First, it determines whether a computation task from the UE should be processed by a specific MEC entity based on current load distribution. This ensures that tasks are assigned to the most suitable edge server to balance workload and avoid overloading any single entity. Second, the procedure assesses whether the UE is likely to leave the coverage area of the assigned MEC entity using mobility-related data, such as movement speed or direction. This prevents unnecessary offloading to edge servers that the UE will soon exit, reducing task interruptions and improving efficiency. By integrating these assessments, the method dynamically optimizes computation offloading decisions, enhancing resource utilization and maintaining service continuity as UEs move within the network. The approach is particularly useful in scenarios with high mobility, such as vehicular networks or smart city applications, where traditional static offloading strategies fail to adapt to changing conditions.
9. The method of claim 1 , wherein the UE mobility-related information includes at least one of velocity information, acceleration information, direction information and location information.
This invention relates to wireless communication systems, specifically to methods for enhancing mobility management in user equipment (UE) devices. The problem addressed is the need for more accurate and efficient tracking of UE mobility to optimize network performance, resource allocation, and service delivery. The method involves collecting and utilizing UE mobility-related information to improve network operations. This information includes velocity, acceleration, direction, and location data, which are used to predict and adapt to the movement patterns of the UE. By analyzing these parameters, the network can make informed decisions about handover procedures, resource allocation, and service optimization, leading to reduced latency, improved reliability, and better overall user experience. The mobility-related data is gathered through various means, such as GPS, inertial sensors, or network-based positioning techniques. The system processes this information in real-time or near-real-time to dynamically adjust network configurations. For example, if a UE is moving at high velocity in a specific direction, the network may preemptively allocate resources along the predicted path to ensure seamless connectivity. Similarly, acceleration data can help anticipate sudden changes in movement, allowing the network to proactively manage handover procedures. The invention also supports the integration of multiple mobility parameters, enabling a more comprehensive understanding of UE behavior. This holistic approach enhances the accuracy of mobility predictions and allows for more precise network adjustments. The system can be applied in various wireless communication standards, including 5G and beyond, to support advanced use cases such as autonomous vehicles, drones, and in
10. An Mobile Edge Computing (MEC) orchestrator, comprising: one or more non-transitory computer-readable media having computer-executable instructions embodied thereon; and at least one processor coupled to the one or more non-transitory computer-readable media, and configured to execute the computer-executable instructions to: acquire MEC computation-related information and User Equipment (UE) mobility-related information from an MEC system including a plurality of MEC entities; perform a classification procedure, based on the MEC computation-related information and the UE mobility-related information, to determine a behavior type of a UE, the behavior type indicating whether to trigger a handover (HO) in the MEC system and whether to trigger a Virtual Machine (VM) migration in the MEC system; compare a system computation loading with one or more loading thresholds to determine a system computation loading level; perform one of a plurality of adjustment procedures in response to the system computation loading level, wherein the adjustment procedures include: a first adjustment procedure to turn off a computation node of a first MEC entity that operates in an idle state; a second adjustment procedure to adjust an operation state or a loading state of a second MEC entity in response to an adjustment request from the second MEC entity; and a third adjustment procedure to offload a computation loading from a third MEC entity to a fourth MEC entity; and provide an instruction table in response to the behavior type, the instruction table including routing information for routing MEC traffic among one or more of the plurality of MEC entities.
This invention relates to Mobile Edge Computing (MEC) systems, specifically addressing the challenges of efficiently managing computation and mobility in distributed MEC environments. The system includes an MEC orchestrator that collects computation-related and mobility-related data from multiple MEC entities. Using this data, the orchestrator classifies the behavior of User Equipment (UE) to determine whether to trigger a handover (HO) or a Virtual Machine (VM) migration. The orchestrator also assesses system computation loading by comparing it to predefined thresholds to determine the loading level. Based on this assessment, it executes one of several adjustment procedures: turning off idle computation nodes, adjusting the operation or loading state of a MEC entity in response to its request, or offloading computation from one MEC entity to another. Additionally, the orchestrator generates an instruction table containing routing information to manage MEC traffic among the MEC entities. This approach optimizes resource utilization and ensures efficient traffic routing in dynamic MEC environments.
11. The MEC orchestrator of claim 10 , wherein the instruction table comprises a VM identity (ID), a UE ID, and a task tag associated with the routing information.
A system for managing mobile edge computing (MEC) resources optimizes task routing in a distributed computing environment. The system addresses inefficiencies in task allocation by dynamically associating computing tasks with specific virtual machines (VMs) and user equipment (UE) devices. This ensures low-latency processing by routing tasks to the nearest or most suitable MEC node based on real-time conditions. The MEC orchestrator maintains an instruction table that includes a VM identity (ID), a UE ID, and a task tag linked to routing information. The VM ID identifies the virtual machine responsible for executing the task, while the UE ID specifies the user device generating or requiring the task. The task tag categorizes the task type or priority, enabling intelligent routing decisions. The routing information directs the task to the appropriate MEC node, optimizing performance and resource utilization. This approach reduces latency and improves efficiency in edge computing environments by ensuring tasks are processed by the most suitable VMs near the relevant UE devices. The system dynamically updates the instruction table to adapt to changing network conditions, ensuring optimal task distribution.
12. The MEC orchestrator of claim 11 , wherein the task tag is generated from the UE ID and the VM ID.
The invention relates to mobile edge computing (MEC) systems, specifically addressing the challenge of efficiently managing and orchestrating tasks within a distributed computing environment. The system includes an MEC orchestrator that dynamically assigns and manages tasks across multiple virtual machines (VMs) to optimize resource utilization and reduce latency. A key feature is the generation of a task tag, which uniquely identifies tasks by combining a user equipment (UE) identifier and a VM identifier. This tagging mechanism ensures traceability and coordination of tasks across the MEC infrastructure, enabling the orchestrator to efficiently allocate resources, monitor task execution, and maintain consistency in a multi-VM environment. The system may also include mechanisms for task prioritization, load balancing, and real-time adjustments based on network conditions or user demands. By integrating UE and VM identifiers into the task tag, the orchestrator can streamline task management, improve system scalability, and enhance overall performance in edge computing applications. The invention is particularly useful in scenarios requiring low-latency processing, such as real-time data analytics, augmented reality, or autonomous vehicle communications.
13. The MEC orchestrator of claim 12 , wherein the task tag is generated by multiplying the UE ID and the VM ID.
The invention relates to mobile edge computing (MEC) systems, specifically addressing the challenge of efficiently managing and orchestrating tasks within a distributed computing environment. The system includes a MEC orchestrator that assigns tasks to virtual machines (VMs) based on unique identifiers to ensure proper task distribution and resource allocation. A key feature is the generation of a task tag by combining a user equipment (UE) identifier and a VM identifier, typically through multiplication, to create a unique tag for each task. This tagging mechanism enables the orchestrator to track and manage tasks across multiple VMs, improving task scheduling, load balancing, and resource utilization. The system ensures that tasks are correctly routed to the appropriate VMs, reducing latency and enhancing overall system efficiency. The MEC orchestrator dynamically assigns tasks based on the generated tags, optimizing performance in edge computing environments where low-latency processing is critical. The invention aims to streamline task management in MEC systems by leveraging unique identifiers to enhance coordination between UEs and VMs.
14. The MEC orchestrator of claim 11 , wherein the instruction table further comprises an MEC entity ID.
A system for managing mobile edge computing (MEC) resources includes an MEC orchestrator that dynamically allocates and configures MEC entities based on network conditions and application requirements. The orchestrator maintains an instruction table that stores configuration parameters for MEC entities, such as virtualized network functions (VNFs) or application services, to optimize performance and resource utilization. The instruction table includes an MEC entity identifier (ID) to uniquely distinguish each MEC entity within the system. This identifier enables the orchestrator to track, manage, and update individual MEC entities efficiently, ensuring proper coordination and communication between distributed MEC components. The system addresses challenges in real-time resource allocation and service deployment in edge computing environments by providing a centralized mechanism for configuring and monitoring MEC entities. The MEC orchestrator dynamically adjusts configurations in response to changing network demands, improving latency, throughput, and reliability for edge-hosted applications. The inclusion of the MEC entity ID in the instruction table ensures accurate identification and management of each entity, preventing conflicts and enhancing system scalability. This approach supports seamless integration of MEC services into existing network infrastructures while optimizing resource usage and service delivery.
15. The MEC orchestrator of claim 10 , wherein the routing information includes: a first routing path indicating a first pair of MEC entities between which a computation loading is to be transmitted, and a second routing path indicating a second pair of MEC entities between which a computation result of the computation loading is to be transmitted.
Multi-access edge computing (MEC) systems enable low-latency processing by distributing computational tasks across edge servers. A key challenge is efficiently routing computation workloads and their results between MEC entities to optimize performance and resource utilization. This invention addresses this by enhancing an MEC orchestrator to manage routing information for computation tasks. The orchestrator includes routing data that specifies two distinct paths: a first path identifies a pair of MEC entities responsible for transmitting a computation workload, while a second path identifies a different pair of MEC entities for transmitting the resulting output. This dual-path routing allows the system to dynamically assign workloads and results to different entity pairs, improving flexibility and load balancing. The routing information may be used to direct computation tasks from a source MEC entity to a target entity for processing, then route the processed results back through a separate path to another entity. This approach ensures efficient task distribution and result retrieval, reducing latency and optimizing resource usage in edge computing environments. The solution is particularly useful in scenarios requiring real-time processing, such as autonomous vehicles or augmented reality applications, where minimizing delay and managing computational loads are critical.
16. The MEC orchestrator of claim 10 , wherein the loading thresholds comprise a first loading threshold and a second loading threshold lower than the first loading threshold, and the at least one processor coupled to the one or more non-transitory computer-readable media is further configured to execute the computer-executable instructions to: perform the first adjustment procedure when the system computation loading is lower than or equal to the second loading threshold; perform the second adjustment procedure when the system computation loading is between the first loading threshold and the second loading threshold and the adjustment request is received; and perform the third adjustment procedure when the system computation loading is greater than or equal to the first loading threshold.
This invention relates to multi-access edge computing (MEC) systems, specifically addressing the dynamic adjustment of computational resources based on system loading to optimize performance and resource utilization. The problem solved involves efficiently managing computational workloads in MEC environments where varying demands require adaptive resource allocation to prevent overloading or underutilization. The system includes an MEC orchestrator that monitors system computation loading and adjusts resources based on predefined thresholds. The orchestrator uses three distinct adjustment procedures triggered by different loading conditions. A first adjustment procedure is performed when the system computation loading is at or below a lower threshold, ensuring minimal resource usage. A second adjustment procedure is activated when the loading is between the lower and higher thresholds and an adjustment request is received, allowing for conditional scaling. A third adjustment procedure is executed when the loading meets or exceeds the higher threshold, prioritizing resource allocation to handle peak demands. The thresholds define the boundaries for triggering each procedure, ensuring that resource adjustments are made proactively or reactively based on current system conditions. This approach optimizes computational efficiency by dynamically scaling resources in response to real-time loading, preventing bottlenecks during high demand while conserving resources during low demand. The system enhances MEC performance by balancing workload distribution and resource allocation.
17. The MEC orchestrator of claim 10 , wherein the classification procedure includes: determining, according to the MEC computation-related information, whether a computation loading distributed from the UE is to be computed on one of the plurality of MEC entities; and determining, according to the UE mobility-related information, whether the UE leaves a coverage area of the one of the plurality of MEC entities.
This invention relates to mobile edge computing (MEC) systems, specifically addressing the challenge of efficiently managing computation tasks in a distributed MEC environment while accounting for user equipment (UE) mobility. The system includes an MEC orchestrator that classifies computation tasks based on both computation-related and mobility-related information. The orchestrator determines whether a computation task offloaded from a UE should be processed by a specific MEC entity, considering factors such as computational load, resource availability, and latency requirements. Additionally, the orchestrator assesses UE mobility patterns to predict whether the UE will leave the coverage area of the assigned MEC entity, ensuring seamless task migration or handover if necessary. This approach optimizes resource utilization, reduces latency, and maintains service continuity as the UE moves between different MEC coverage areas. The system dynamically adjusts task allocation based on real-time conditions, improving overall efficiency and reliability in MEC deployments.
18. The MEC orchestrator of claim 10 , wherein the UE mobility-related information includes at least one of velocity information, acceleration information, direction information and location information.
The invention relates to mobile edge computing (MEC) systems, specifically focusing on optimizing network resource allocation and service delivery based on user equipment (UE) mobility characteristics. The problem addressed is the inefficient use of network resources when MEC systems lack real-time awareness of UE movement patterns, leading to suboptimal service placement and performance degradation. The MEC orchestrator collects and processes UE mobility-related information, including velocity, acceleration, direction, and location data. This information is used to predict UE movement patterns and dynamically adjust MEC service deployment. For example, if a UE is moving at high velocity, the orchestrator may prioritize offloading tasks to edge nodes along the predicted path to minimize latency. Similarly, acceleration and direction data help anticipate changes in movement, allowing proactive resource allocation. Location information ensures services are deployed in proximity to the UE, reducing network strain and improving responsiveness. By integrating these mobility metrics, the MEC orchestrator enhances service continuity, reduces latency, and optimizes resource utilization in dynamic environments. The system adapts to real-time mobility changes, ensuring seamless service delivery as the UE moves across different network segments. This approach is particularly beneficial in scenarios like vehicular networks, smart cities, and industrial IoT, where UE mobility significantly impacts performance. The solution leverages existing mobility data to make intelligent decisions, avoiding the need for additional infrastructure or complex algorithms.
Unknown
May 19, 2020
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.